INDEX

Explanations

references to awards and accolades

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Иль

-0.68

pse

-0.66

Hu

-0.66

ilirsiniz

-0.65

ities

-0.65

 Pyle

-0.64

❧

-0.64

führt

-0.63

кас

-0.63

SequentialGroup

-0.63

POSITIVE LOGITS

 awards

2.34

 award

2.19

 Awards

2.19

 Award

2.13

awards

2.07

 AWARD

2.06

Award

2.05

 AWARDS

1.99

Awards

1.95

award

1.88

Activations Density 0.062%

references to awards and accolades

No Comments

No Known Activations